versionhq 1.1.7.3__tar.gz → 1.1.7.5__tar.gz

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: versionhq
-Version: 1.1.7.3
+Version: 1.1.7.5
 Summary: LLM orchestration frameworks for model-agnostic AI agents that handle complex outbound workflows
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -52,7 +52,11 @@ Requires-Dist: wheel>=0.45.1
 
 # Overview
 
-![MIT license](https://img.shields.io/badge/License-MIT-green) [![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml) ![PyPi](https://img.shields.io/badge/pypi-v1.1.7.0-blue) ![python ver](https://img.shields.io/badge/Python-3.12/3.13-purple) ![pyenv ver](https://img.shields.io/badge/pyenv-2.4.23-orange)
+![MIT license](https://img.shields.io/badge/License-MIT-green)
+[![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml)
+![PyPI](https://img.shields.io/badge/PyPI-v1.1.7.5-blue)
+![python ver](https://img.shields.io/badge/Python-3.12/3.13-purple)
+![pyenv ver](https://img.shields.io/badge/pyenv-2.4.23-orange)
 
 
 An LLM orchestration frameworks for multi-agent systems with RAG to autopilot outbound workflows.
@@ -64,10 +68,11 @@ Messaging workflows are created at individual level, and will be deployed on thi
 
 **Visit:**
 
-- [Landing page](https://home.versi0n.io)
-- [Client app](https://versi0n.io/)
-- [Orchestration frameworks](https://github.com/versionHQ/multi-agent-system)
-- [Test client app](https://github.com/versionHQ/test-client-app)
+- [PyPI](https://pypi.org/project/versionhq/)
+- [Github (LLM orchestration)](https://github.com/versionHQ/multi-agent-system)
+- [Github (Test client app)](https://github.com/versionHQ/test-client-app)
+- [Use case](https://versi0n.io/) - client app (alpha)
+
 
 <hr />
 
@@ -87,6 +92,8 @@ LLM-powered `agent`s and `team`s use `tool`s and their own knowledge to complete
 
 - [Key Features](#key-features)
 - [Usage](#usage)
+  - [Case 1. Build an AI agent on LLM of your choice and execute a task:](#case-1-build-an-ai-agent-on-llm-of-your-choice-and-execute-a-task)
+  - [Case 2. Form a team to handle multiple tasks:](#case-2-form-a-team-to-handle-multiple-tasks)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
 - [Setup](#setup)
@@ -132,7 +139,8 @@ Multiple `agents` can form a `team` to complete complex tasks together.
 
 2. You can use the `versionhq` module in your Python app.
 
-   - **i.e.,** Make LLM-based agent execute the task and return JSON dict.
+
+### Case 1. Build an AI agent on LLM of your choice and execute a task:
 
    ```
    from versionhq.agent.model import Agent
@@ -142,6 +150,7 @@ Multiple `agents` can form a `team` to complete complex tasks together.
       role="demo",
       goal="amazing project goal",
       skillsets=["skill_1", "skill_2", ],
+      tools=["amazing RAG tool",]
       llm="llm-of-your-choice"
    )
 
@@ -165,7 +174,41 @@ This will return a dictionary with keys defined in the `ResponseField`.
    { test1: "answer1", "test2": ["answer2-1", "answer2-2", "answer2-3",] }
    ```
 
-For more info: [PyPI package](https://pypi.org/project/versionhq/)
+### Case 2. Form a team to handle multiple tasks:
+
+   ```
+   from versionhq.agent.model import Agent
+   from versionhq.task.model import Task, ResponseField
+   from versionhq.team.model import Team, TeamMember
+
+   agent_a = Agent(role="agent a", goal="My amazing goals", llm="llm-of-your-choice")
+   agent_b = Agent(role="agent b", goal="My amazing goals", llm="llm-of-your-choice")
+
+   task_1 = Task(
+      description="Analyze the client's business model.",
+      output_field_list=[ResponseField(title="test1", type=str, required=True),],
+      allow_delegation=True
+   )
+
+    task_2 = Task(
+      description="Define the cohort.",
+      output_field_list=[ResponseField(title="test1", type=int, required=True),],
+      allow_delegation=False
+   )
+
+   team = Team(
+      members=[
+         TeamMember(agent=agent_a, is_manager=False, task=task_1),
+         TeamMember(agent=agent_b, is_manager=True, task=task_2),
+      ],
+   )
+   res = team.kickoff()
+   ```
+
+This will return a list with dictionaries with keys defined in the `ResponseField` of each task.
+
+Tasks can be delegated to a team manager, peers in the team, or completely new agent.
+
 
 <hr />
 

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/README.md

@@ -1,6 +1,10 @@
 # Overview
 
-![MIT license](https://img.shields.io/badge/License-MIT-green) [![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml) ![PyPi](https://img.shields.io/badge/pypi-v1.1.7.0-blue) ![python ver](https://img.shields.io/badge/Python-3.12/3.13-purple) ![pyenv ver](https://img.shields.io/badge/pyenv-2.4.23-orange)
+![MIT license](https://img.shields.io/badge/License-MIT-green)
+[![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml)
+![PyPI](https://img.shields.io/badge/PyPI-v1.1.7.5-blue)
+![python ver](https://img.shields.io/badge/Python-3.12/3.13-purple)
+![pyenv ver](https://img.shields.io/badge/pyenv-2.4.23-orange)
 
 
 An LLM orchestration frameworks for multi-agent systems with RAG to autopilot outbound workflows.
@@ -12,10 +16,11 @@ Messaging workflows are created at individual level, and will be deployed on thi
 
 **Visit:**
 
-- [Landing page](https://home.versi0n.io)
-- [Client app](https://versi0n.io/)
-- [Orchestration frameworks](https://github.com/versionHQ/multi-agent-system)
-- [Test client app](https://github.com/versionHQ/test-client-app)
+- [PyPI](https://pypi.org/project/versionhq/)
+- [Github (LLM orchestration)](https://github.com/versionHQ/multi-agent-system)
+- [Github (Test client app)](https://github.com/versionHQ/test-client-app)
+- [Use case](https://versi0n.io/) - client app (alpha)
+
 
 <hr />
 
@@ -35,6 +40,8 @@ LLM-powered `agent`s and `team`s use `tool`s and their own knowledge to complete
 
 - [Key Features](#key-features)
 - [Usage](#usage)
+  - [Case 1. Build an AI agent on LLM of your choice and execute a task:](#case-1-build-an-ai-agent-on-llm-of-your-choice-and-execute-a-task)
+  - [Case 2. Form a team to handle multiple tasks:](#case-2-form-a-team-to-handle-multiple-tasks)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
 - [Setup](#setup)
@@ -80,7 +87,8 @@ Multiple `agents` can form a `team` to complete complex tasks together.
 
 2. You can use the `versionhq` module in your Python app.
 
-   - **i.e.,** Make LLM-based agent execute the task and return JSON dict.
+
+### Case 1. Build an AI agent on LLM of your choice and execute a task:
 
    ```
    from versionhq.agent.model import Agent
@@ -90,6 +98,7 @@ Multiple `agents` can form a `team` to complete complex tasks together.
       role="demo",
       goal="amazing project goal",
       skillsets=["skill_1", "skill_2", ],
+      tools=["amazing RAG tool",]
       llm="llm-of-your-choice"
    )
 
@@ -113,7 +122,41 @@ This will return a dictionary with keys defined in the `ResponseField`.
    { test1: "answer1", "test2": ["answer2-1", "answer2-2", "answer2-3",] }
    ```
 
-For more info: [PyPI package](https://pypi.org/project/versionhq/)
+### Case 2. Form a team to handle multiple tasks:
+
+   ```
+   from versionhq.agent.model import Agent
+   from versionhq.task.model import Task, ResponseField
+   from versionhq.team.model import Team, TeamMember
+
+   agent_a = Agent(role="agent a", goal="My amazing goals", llm="llm-of-your-choice")
+   agent_b = Agent(role="agent b", goal="My amazing goals", llm="llm-of-your-choice")
+
+   task_1 = Task(
+      description="Analyze the client's business model.",
+      output_field_list=[ResponseField(title="test1", type=str, required=True),],
+      allow_delegation=True
+   )
+
+    task_2 = Task(
+      description="Define the cohort.",
+      output_field_list=[ResponseField(title="test1", type=int, required=True),],
+      allow_delegation=False
+   )
+
+   team = Team(
+      members=[
+         TeamMember(agent=agent_a, is_manager=False, task=task_1),
+         TeamMember(agent=agent_b, is_manager=True, task=task_2),
+      ],
+   )
+   res = team.kickoff()
+   ```
+
+This will return a list with dictionaries with keys defined in the `ResponseField` of each task.
+
+Tasks can be delegated to a team manager, peers in the team, or completely new agent.
+
 
 <hr />
 

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/pyproject.toml

@@ -15,7 +15,7 @@ exclude = ["test*", "__pycache__"]
 
 [project]
 name = "versionhq"
-version = "1.1.7.3"
+version = "1.1.7.5"
 authors = [{ name = "Kuriko Iwai", email = "kuriko@versi0n.io" }]
 description = "LLM orchestration frameworks for model-agnostic AI agents that handle complex outbound workflows"
 readme = "README.md"

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/src/versionhq/__init__.py

@@ -17,7 +17,7 @@ from versionhq.team.model import Team, TeamOutput
 from versionhq.tool.model import Tool
 
 
-__version__ = "1.1.7.3"
+__version__ = "1.1.7.5"
 __all__ = [
     "Agent",
     "Customer",

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/src/versionhq/clients/workflow/model.py

@@ -61,21 +61,21 @@ class MessagingComponent(ABC, BaseModel):
     score: Union[float, InstanceOf[Score]] = Field(default=None)
 
 
-    def store_scoring_result(self, scoring_subject: str, score: Union[int, Score, ScoreFormat] = None):
+    def store_scoring_result(self, scoring_subject: str, score_raw: Union[int, Score, ScoreFormat] = None):
         """
         Set up the `score` field
         """
 
-        if isinstance(score, Score):
-            setattr(self, "score", score)
+        if isinstance(score_raw, Score):
+            setattr(self, "score", score_raw)
 
-        elif isinstance(score, ScoreFormat):
+        elif isinstance(score_raw, ScoreFormat):
             score_instance = Score()
-            setattr(score_instance, scoring_subject, score)
+            setattr(score_instance, scoring_subject, score_raw)
             setattr(self, "score", score_instance)
 
-        elif isinstance(score, int) or isinstance(score, float):
-            score_instance, score_format_instance = Score(), ScoreFormat(rate=score, weight=1)
+        elif isinstance(score_raw, int) or isinstance(score_raw, float):
+            score_instance, score_format_instance = Score(), ScoreFormat(rate=score_raw, weight=1)
             setattr(score_instance, "kwargs", { scoring_subject: score_format_instance })
             setattr(self, "score", score_instance)
 

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/src/versionhq/task/model.py

@@ -158,6 +158,7 @@ class Task(BaseModel):
     async_execution: bool = Field(default=False,description="whether the task should be executed asynchronously or not")
     config: Optional[Dict[str, Any]] = Field(default=None, description="configuration for the agent")
     callback: Optional[Any] = Field(default=None, description="callback to be executed after the task is completed.")
+    callback_kwargs: Optional[Dict[str, Any]] = Field(default_factory=dict, description="kwargs for the callback when the callback is callable")
 
     # recording
     processed_by_agents: Set[str] = Field(default_factory=set)
@@ -371,7 +372,7 @@ Your outputs MUST adhere to the following format and should NOT include any irre
 
 
     # task execution
-    def execute_sync(self, agent, context: Optional[str] = None, callback_kwargs: Dict[str, Any] = None) -> TaskOutput:
+    def execute_sync(self, agent, context: Optional[str] = None) -> TaskOutput:
         """
         Execute the task synchronously.
         When the task has context, make sure we have executed all the tasks in the context first.
@@ -380,12 +381,12 @@ Your outputs MUST adhere to the following format and should NOT include any irre
         if self.context:
             for task in self.context:
                 if task.output is None:
-                    task._execute_core(agent, context, callback_kwargs)
+                    task._execute_core(agent, context)
 
         return self._execute_core(agent, context)
 
 
-    def execute_async(self, agent, context: Optional[str] = None, callback_kwargs: Dict[str, Any] = None) -> Future[TaskOutput]:
+    def execute_async(self, agent, context: Optional[str] = None) -> Future[TaskOutput]:
         """
         Execute the task asynchronously.
         """
@@ -394,36 +395,55 @@ Your outputs MUST adhere to the following format and should NOT include any irre
         threading.Thread(
             daemon=True,
             target=self._execute_task_async,
-            args=(agent, context, callback_kwargs, future),
+            args=(agent, context, future),
         ).start()
         return future
 
 
-    def _execute_task_async(self, agent, context: Optional[str], callback_kwargs: Dict[str, Any], future: Future[TaskOutput]) -> None:
+    def _execute_task_async(self, agent, context: Optional[str], future: Future[TaskOutput]) -> None:
         """
         Execute the task asynchronously with context handling.
         """
 
-        result = self._execute_core(agent, context, callback_kwargs)
+        result = self._execute_core(agent, context)
         future.set_result(result)
 
 
-    def _execute_core(self, agent, context: Optional[str], callback_kwargs: Optional[Dict[str, Any]] = None) -> TaskOutput:
+    def _execute_core(self, agent, context: Optional[str]) -> TaskOutput:
         """
         Run the core execution logic of the task.
         To speed up the process, when the format is not expected to return, we will skip the conversion process.
+        When the task is allowed to delegate to another agent, we will select a responsible one in order of manager_agent > peer_agent > anoymous agent.
         """
         from versionhq.agent.model import Agent
+        from versionhq.team.model import Team
 
         self.prompt_context = context
 
         if self.allow_delegation:
-            agent = Agent(role="delegated_agent", goal=agent.goal, llm=agent.llm) #! REFINEME - logic to pick up the high performer
+            agent_to_delegate = None
+
+            if hasattr(agent, "team") and isinstance(agent.team, Team):
+                if agent.team.manager_agent:
+                    agent_to_delegate = agent.team.manager_agent
+                else:
+                    peers = [member.agent for member in agent.team.members if member.is_manager == False and member.agent.id is not agent.id]
+                    if len(peers) > 0:
+                        agent_to_delegate = peers[0]
+            else:
+                agent_to_delegate = Agent(role="delegated_agent", goal=agent.goal, llm=agent.llm)
+
+            agent = agent_to_delegate
             self.delegations += 1
 
-        output_raw = agent.execute_task(task=self, context=context)
-        output_json_dict = self.create_json_output(raw_result=output_raw) if self.expected_output_json is True else None
-        output_pydantic = self.create_pydantic_output(output_json_dict=output_json_dict) if self.expected_output_pydantic else None
+        output_raw, output_json_dict, output_pydantic = agent.execute_task(task=self, context=context), None, None
+
+        if self.expected_output_json:
+            output_json_dict = self.create_json_output(raw_result=output_raw)
+
+        if self.expected_output_pydantic:
+            output_pydantic = self.create_pydantic_output(output_json_dict=output_json_dict)
+
         task_output = TaskOutput(
             task_id=self.id,
             raw=output_raw,
@@ -436,10 +456,7 @@ Your outputs MUST adhere to the following format and should NOT include any irre
         # self._set_end_execution_time(start_time)
 
         if self.callback:
-            if isinstance(self.callback, Callable):
-                self.callback(**callback_kwargs)
-            else:
-                self.callback(self.output)
+            self.callback({ **self.callback_kwargs, **self.output.__dict__ })
 
         # if self._execution_span:
         #     # self._telemetry.task_ended(self._execution_span, self, agent.team)

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/src/versionhq/team/model.py

@@ -111,7 +111,7 @@ class TeamOutput(BaseModel):
 class TeamMember(ABC, BaseModel):
     agent: Agent | None = Field(default=None, description="store the agent to be a member")
     is_manager: bool = Field(default=False)
-    task: Task | None = Field(default=None)
+    task: Optional[Task] = Field(default=None)
 
 
 class Team(BaseModel):
@@ -145,7 +145,6 @@ class Team(BaseModel):
         default_factory=list,
         description="list of callback functions to be executed after the team kickoff. i.e., store the result in repo"
     )
-    task_callback: Optional[Any] = Field(default=None, description="callback to be executed after each task for all agents execution")
     step_callback: Optional[Any] = Field(default=None, description="callback to be executed after each step for all agents execution")
 
     verbose: bool = Field(default=True)
@@ -379,7 +378,7 @@ class Team(BaseModel):
         """
         Executes tasks sequentially and returns the final output in TeamOutput class.
         When we have a manager agent, we will start from executing manager agent's tasks.
-        Priority
+        Priority:
         1. Team tasks > 2. Manager task > 3. Member tasks (in order of index)
         """
 
@@ -412,7 +411,7 @@ class Team(BaseModel):
 
             if task.async_execution:
                 context = create_raw_outputs(tasks=[task, ],task_outputs=([last_sync_output,] if last_sync_output else []))
-                future = task.execute_async(agent=responsible_agent, context=context,
+                future = task.execute_async(agent=responsible_agent, context=context
                                             # tools=responsible_agent.tools
                                             )
                 futures.append((task, future, task_index))
@@ -422,7 +421,7 @@ class Team(BaseModel):
                     futures.clear()
 
                 context = create_raw_outputs(tasks=[task,], task_outputs=([ last_sync_output,] if last_sync_output else [] ))
-                task_output = task.execute_sync(agent=responsible_agent, context=context,
+                task_output = task.execute_sync(agent=responsible_agent, context=context
                                                 # tools=responsible_agent.tools
                                                 )
                 if responsible_agent is self.manager_agent:
@@ -463,9 +462,6 @@ class Team(BaseModel):
         #     self._inputs = inputs
         # self._interpolate_inputs(inputs)
 
-        for task in self.tasks:
-            if not task.callback:
-                task.callback = self.task_callback
 
         # i18n = I18N(prompt_file=self.prompt_file)
 

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/src/versionhq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: versionhq
-Version: 1.1.7.3
+Version: 1.1.7.5
 Summary: LLM orchestration frameworks for model-agnostic AI agents that handle complex outbound workflows
 Author-email: Kuriko Iwai <kuriko@versi0n.io>
 License: MIT License
@@ -52,7 +52,11 @@ Requires-Dist: wheel>=0.45.1
 
 # Overview
 
-![MIT license](https://img.shields.io/badge/License-MIT-green) [![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml) ![PyPi](https://img.shields.io/badge/pypi-v1.1.7.0-blue) ![python ver](https://img.shields.io/badge/Python-3.12/3.13-purple) ![pyenv ver](https://img.shields.io/badge/pyenv-2.4.23-orange)
+![MIT license](https://img.shields.io/badge/License-MIT-green)
+[![Publisher](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml/badge.svg)](https://github.com/versionHQ/multi-agent-system/actions/workflows/publish.yml)
+![PyPI](https://img.shields.io/badge/PyPI-v1.1.7.5-blue)
+![python ver](https://img.shields.io/badge/Python-3.12/3.13-purple)
+![pyenv ver](https://img.shields.io/badge/pyenv-2.4.23-orange)
 
 
 An LLM orchestration frameworks for multi-agent systems with RAG to autopilot outbound workflows.
@@ -64,10 +68,11 @@ Messaging workflows are created at individual level, and will be deployed on thi
 
 **Visit:**
 
-- [Landing page](https://home.versi0n.io)
-- [Client app](https://versi0n.io/)
-- [Orchestration frameworks](https://github.com/versionHQ/multi-agent-system)
-- [Test client app](https://github.com/versionHQ/test-client-app)
+- [PyPI](https://pypi.org/project/versionhq/)
+- [Github (LLM orchestration)](https://github.com/versionHQ/multi-agent-system)
+- [Github (Test client app)](https://github.com/versionHQ/test-client-app)
+- [Use case](https://versi0n.io/) - client app (alpha)
+
 
 <hr />
 
@@ -87,6 +92,8 @@ LLM-powered `agent`s and `team`s use `tool`s and their own knowledge to complete
 
 - [Key Features](#key-features)
 - [Usage](#usage)
+  - [Case 1. Build an AI agent on LLM of your choice and execute a task:](#case-1-build-an-ai-agent-on-llm-of-your-choice-and-execute-a-task)
+  - [Case 2. Form a team to handle multiple tasks:](#case-2-form-a-team-to-handle-multiple-tasks)
 - [Technologies Used](#technologies-used)
 - [Project Structure](#project-structure)
 - [Setup](#setup)
@@ -132,7 +139,8 @@ Multiple `agents` can form a `team` to complete complex tasks together.
 
 2. You can use the `versionhq` module in your Python app.
 
-   - **i.e.,** Make LLM-based agent execute the task and return JSON dict.
+
+### Case 1. Build an AI agent on LLM of your choice and execute a task:
 
    ```
    from versionhq.agent.model import Agent
@@ -142,6 +150,7 @@ Multiple `agents` can form a `team` to complete complex tasks together.
       role="demo",
       goal="amazing project goal",
       skillsets=["skill_1", "skill_2", ],
+      tools=["amazing RAG tool",]
       llm="llm-of-your-choice"
    )
 
@@ -165,7 +174,41 @@ This will return a dictionary with keys defined in the `ResponseField`.
    { test1: "answer1", "test2": ["answer2-1", "answer2-2", "answer2-3",] }
    ```
 
-For more info: [PyPI package](https://pypi.org/project/versionhq/)
+### Case 2. Form a team to handle multiple tasks:
+
+   ```
+   from versionhq.agent.model import Agent
+   from versionhq.task.model import Task, ResponseField
+   from versionhq.team.model import Team, TeamMember
+
+   agent_a = Agent(role="agent a", goal="My amazing goals", llm="llm-of-your-choice")
+   agent_b = Agent(role="agent b", goal="My amazing goals", llm="llm-of-your-choice")
+
+   task_1 = Task(
+      description="Analyze the client's business model.",
+      output_field_list=[ResponseField(title="test1", type=str, required=True),],
+      allow_delegation=True
+   )
+
+    task_2 = Task(
+      description="Define the cohort.",
+      output_field_list=[ResponseField(title="test1", type=int, required=True),],
+      allow_delegation=False
+   )
+
+   team = Team(
+      members=[
+         TeamMember(agent=agent_a, is_manager=False, task=task_1),
+         TeamMember(agent=agent_b, is_manager=True, task=task_2),
+      ],
+   )
+   res = team.kickoff()
+   ```
+
+This will return a list with dictionaries with keys defined in the `ResponseField` of each task.
+
+Tasks can be delegated to a team manager, peers in the team, or completely new agent.
+
 
 <hr />
 

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/tests/clients/workflow_test.py

@@ -15,7 +15,7 @@ def test_store_scores():
 
     messaging_component = MessagingComponent(message="demo")
     score_raw = 15
-    messaging_component.store_scoring_result("demo", score=score_raw)
+    messaging_component.store_scoring_result("demo", score_raw=score_raw)
 
     assert messaging_component.score is not None
     assert messaging_component.score.result() is not None

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/tests/task/task_test.py

@@ -1,7 +1,7 @@
 import os
 import pytest
 from unittest.mock import patch
-from typing import Union
+from typing import Union, Dict, Any
 from versionhq.agent.model import Agent
 from versionhq.task.model import Task, ResponseField, TaskOutput, AgentOutput
 
@@ -27,8 +27,6 @@ def test_sync_execute_task():
             ResponseField(title="test1", type=str, required=True),
             ResponseField(title="test2", type=list, required=True),
         ],
-        context=None,
-        callback=None,
     )
     res = task.execute_sync(agent=agent)
 
@@ -202,14 +200,14 @@ def test_callback():
     See if the callback function is executed well with kwargs.
     """
 
-    def callback_func(item: str = None):
-        return f"I am callback with {item}."
-
-    agent = Agent(
-        role="demo agent 5",
-        goal="My amazing goals",
-    )
+    def callback_func(kwargs: Dict[str, Any]):
+        task_id = kwargs.get("task_id", None)
+        added_condition = kwargs.get("added_condition", None)
+        assert task_id is not None
+        assert added_condition is not None
+        return f"Result: {task_id}, condition added: {added_condition}"
 
+    agent = Agent(role="demo agent 5", goal="My amazing goals")
     task = Task(
         description="Analyze the client's business model and define the optimal cohort timeframe.",
         expected_output_json=True,
@@ -217,23 +215,27 @@ def test_callback():
         output_field_list=[
             ResponseField(title="test1", type=str, required=True),
         ],
-        callback=callback_func
+        callback=callback_func,
+        callback_kwargs=dict(added_condition="demo for pytest")
     )
 
-    with patch.object(Agent, "execute_task", return_value="ok") as execute:
-        execution = task.execute_async(agent=agent, callback_kwargs={"item": "demo for pytest"})
-        result = execution.result()
-        assert result.raw == "ok"
-        execute.assert_called_once_with(task=task, context=None)
+    res = task.execute_sync(agent=agent)
 
+    assert res is not None
+    assert isinstance(res, TaskOutput)
+    assert res.task_id is task.id
+    assert res.raw is not None
+
+    # with patch.object(Agent, "execute_task", return_value="ok") as execute:
+    #     execution = task.execute_async(agent=agent)
+    #     result = execution.result()
+    #     assert result.raw == "ok"
+    #     execute.assert_called_once_with(task=task, context=None)
 
 
-def test_delegate():
-    agent = Agent(
-        role="demo agent 6",
-        goal="My amazing goals",
-    )
 
+def test_delegate():
+    agent = Agent(role="demo agent 6", goal="My amazing goals")
     task = Task(
         description="Analyze the client's business model and define the optimal cohort timeframe.",
         expected_output_json=True,
@@ -254,5 +256,4 @@ def test_delegate():
 # def test_conditional_task():
 
 
-
 # tools, CONDITIONAL, token usage

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/tests/team/team_test.py

@@ -192,17 +192,105 @@ def test_kickoff_team_without_leader():
     assert len(res_all) == 2
     for item in res_all:
         assert isinstance(item, dict)
-        # if not hasattr(item, "output") and not hasattr(res_all, "output"):
-        #     assert "test1" in item
-        #     assert "test2" in item
-        # else:
-        #     assert "output" in item
-
     assert isinstance(res.token_usage, UsageMetrics)
     assert res.token_usage.total_tokens == 0 # as we dont set token usage on agent
 
 
 
+def team_kickoff_with_task_callback():
+    """
+    Each task has callback with callback kwargs.
+    """
+    demo_list = []
+    def demo_callback(item: str) -> None:
+        demo_list.append(item)
+
+    agent_a = Agent(
+        role="agent a",
+        goal="My amazing goals",
+        llm=MODEL_NAME
+    )
+
+    agent_b = Agent(
+        role="agent b",
+        goal="My amazing goals",
+        llm=MODEL_NAME
+    )
+
+    task_1 = Task(
+        description="Analyze the client's business model.",
+        output_field_list=[ResponseField(title="test1", type=str, required=True),],
+        callback=demo_callback,
+        callback_kwargs=dict(item="pytest demo 1")
+    )
+
+    task_2 = Task(
+        description="Define the cohort.",
+        output_field_list=[ResponseField(title="test1", type=int, required=True),],
+        callback=demo_callback,
+        callback_kwargs=dict(item="pytest demo 2")
+    )
+
+    team = Team(
+        members=[
+            TeamMember(agent=agent_a, is_manager=False, task=task_1),
+            TeamMember(agent=agent_b, is_manager=False, task=task_2),
+        ],
+    )
+    res = team.kickoff()
+
+    assert res.raw is not None
+    assert res.json_dict is not None
+    assert len(res.return_all_task_outputs()) == 2
+    assert len(demo_list) == 2
+    assert "pytest" in demo_list[0]
+    assert "pytest" in demo_list[1]
+
+
+
+def test_delegate_in_team():
+    """
+    When the agent belongs to the team, the team manager or peers are prioritized to delegete the task.
+    """
+
+    agent_a = Agent(
+        role="agent a",
+        goal="My amazing goals",
+        llm=MODEL_NAME
+    )
+
+    agent_b = Agent(
+        role="agent b",
+        goal="My amazing goals",
+        llm=MODEL_NAME
+    )
+
+    task_1 = Task(
+        description="Analyze the client's business model.",
+        output_field_list=[ResponseField(title="test1", type=str, required=True),],
+        allow_delegation=True
+    )
+
+    task_2 = Task(
+        description="Define the cohort.",
+        output_field_list=[ResponseField(title="test1", type=int, required=True),],
+        allow_delegation=False
+    )
+
+    team = Team(
+        members=[
+            TeamMember(agent=agent_a, is_manager=False, task=task_1),
+            TeamMember(agent=agent_b, is_manager=False, task=task_2),
+        ],
+    )
+    res = team.kickoff()
+
+    assert res.raw is not None
+    assert res.json_dict is not None
+    assert "agent b" in task_1.processed_by_agents
+
+
+
 # def test_kickoff_with_team_leader():
 #     agent_a = Agent(
 #         role="Demo Agent A",

{versionhq-1.1.7.3 → versionhq-1.1.7.5}/uv.lock

@@ -1647,7 +1647,7 @@ wheels = [
 
 [[package]]
 name = "versionhq"
-version = "1.1.7.3"
+version = "1.1.7.5"
 source = { editable = "." }
 dependencies = [
     { name = "composio" },